feat: add docs

.gitignore

@@ -24,5 +24,8 @@ apps/elt/logs/**
 
 dist/
 
+# mkdocs build output
+site/
+
 .claude/settings.local.json
 .claude/plans/

.readthedocs.yaml

@@ -0,0 +1,17 @@
+# .readthedocs.yaml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+version: 2
+
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.11"
+
+mkdocs:
+  configuration: mkdocs.yml
+
+python:
+   install:
+   - requirements: mkdocs_requirements.txt

apps/backend/datafeeder.env

@@ -1,13 +1,232 @@
-# Used to override default values in config.py
+# Datafeeder backend configuration reference
+#
+# This file documents every configuration option read by the backend
+# (see apps/backend/src/core/config.py). Each option is listed with its
+# default value and a short description.
+#
+# How configuration is resolved (first source that provides a value for a
+# given setting wins; see settings_customise_sources in config.py):
+#   1. geOrchestra default.properties (datadir/default.properties) [highest priority]
+#   2. Environment variables
+#   3. This .env file (DATAFEEDER_CONFIG or
+#      <datadir>/datafeeder/datafeeder.env)
+#   4. Init/keyword arguments
+#   5. Secret files [lowest priority]
+#
+# Only the values you want to override need to be present; every option below
+# has a default. Uncomment and adapt the ones relevant to your instance.
+#
+# Notes:
+# - Values may reference environment variables with ${VAR} syntax; they are
+#   expanded at load time (see expand_env_vars validator).
+# - Some PostgreSQL options also accept geOrchestra-style aliases coming from
+#   default.properties (pgsqlHost, pgsqlPort, ...). These aliases are noted
+#   below.
+
+### Project information
+
+# Human readable name of the application.
+# Default: Datafeeder
+#PROJECT_NAME=Datafeeder
+
+# Internal URL of the backend, as reachable by other services (server side).
+# Default: http://localhost:8000
 BACKEND_INTERNAL_URL=http://host.docker.internal:8000
-TMP_UPLOAD_PATH=/tmp/
-ENCRYPTION_KEY=your_encryption_key
+
+# Public base URL of the published data service (GeoServer), shown to users.
+# Default: http://localhost:8080/geoserver
+#DATA_PUBLIC_URL=http://localhost:8080/geoserver
+
+# Public URL template of a dataset in Datahub. {metadata_id} is substituted.
+# Default: http://localhost:8080/datahub/dataset/{metadata_id}
+#DATAHUB_PUBLIC_URL=http://localhost:8080/datahub/dataset/{metadata_id}
+
+# Public base URL of the metadata catalog (GeoNetwork), shown to users.
+# Default: http://localhost:8080/geonetwork
+#METADATA_PUBLIC_URL=http://localhost:8080/geonetwork
+
+# Path to the geOrchestra datadir used by the application.
+# Default: resolved by get_default_datadir()
+#DATADIR_PATH=/etc/georchestra
+
+### API configuration
+
+# Deployment environment. Controls strictness of secret validation:
+# in "local" weak secrets only warn, otherwise they raise an error.
+# Allowed values: local, staging, production
+# Default: local
+#ENVIRONMENT=local
+
+# Directory where uploaded files are temporarily stored.
+# Default: /tmp/
+#TMP_UPLOAD_PATH=/tmp/
+
+# JSON array of projections offered to the frontend.
+# Each item is {"value": "<EPSG code>", "label": "<display name>"}.
+# Default: [{"value": "EPSG:4326", "label": "WGS 84"}, {"value": "EPSG:3857", "label": "Web Mercator"}]
+#PROJECTIONS=[{"value": "EPSG:4326", "label": "WGS 84"}, {"value": "EPSG:3857", "label": "Web Mercator"}]
+
+### Security
+
+# Secret key used to sign/secure tokens. Generated randomly if unset.
+# Must NOT be "changethis"; required to be strong outside local environment.
+# Default: randomly generated at startup
+#SECRET_KEY=changeme
+
+# Encryption key used to store sensitive data (e.g. HTTP Basic Auth
+# credentials). Must NOT be "changethis" outside local environment.
+# Default: (empty)
+#ENCRYPTION_KEY=your_encryption_key
+
+### Task executor
+
+# Backend used to run ingestion/processing tasks.
+# Allowed values: AIRFLOW (and other TaskExecutorType members).
+# Default: AIRFLOW
+#TASK_EXECUTOR=AIRFLOW
+
+### Airflow
+
+# Internal URL of the Airflow API/web server.
+# Default: http://localhost:8081/airflow
+#AIRFLOW_INTERNAL_URL=http://localhost:8081/airflow
+
+# Airflow username used by the backend to trigger DAGs.
+# Default: airflow
+#AIRFLOW_USERNAME=airflow
+
+# Airflow password used by the backend to trigger DAGs.
+# Default: airflow
+#AIRFLOW_PASSWORD=airflow
+
+# Lifetime of issued access tokens, in minutes.
+# Default: 11520 (8 days)
+#ACCESS_TOKEN_EXPIRE_MINUTES=11520
+
+# Hour of the day (0-23) at which daily/weekly/monthly/yearly recurrences run.
+# Default: 4
+#RECURRENCE_EXECUTION_HOUR=4
+
+### CORS
+
+# URL of the frontend application; always added to the allowed CORS origins.
+# Default: http://localhost:5173
+#FRONTEND_HOST=http://localhost:5173
+
+# Additional allowed CORS origins. Comma-separated list or a JSON array.
+# Default: (empty)
+#BACKEND_CORS_ORIGINS=http://localhost:5173,http://localhost:8080
+
+### PostgreSQL - Datafeeder application database
+# This is the database holding the application's own data.
+# Aliases from default.properties / generic names are accepted as noted.
+
+# Host of the application database.
+# Aliases accepted: pgsqlHost, POSTGRES_HOST
+# Default: localhost
+#POSTGRES_DATAFEEDER_HOST=localhost
+
+# Port of the application database.
+# Aliases accepted: pgsqlPort, POSTGRES_PORT
+# Default: 5432
+#POSTGRES_DATAFEEDER_PORT=5432
+
+# User of the application database.
+# Aliases accepted: pgsqlUser, POSTGRES_USER
+# Default: georchestra
+#POSTGRES_DATAFEEDER_USER=georchestra
+
+# Password of the application database. Must NOT be "changethis" outside local.
+# Aliases accepted: pgsqlPassword, POSTGRES_PASSWORD
+# Default: georchestra
+#POSTGRES_DATAFEEDER_PASSWORD=georchestra
+
+# Name of the application database.
+# Aliases accepted: pgsqlDatabase, POSTGRES_DB
+# Default: georchestra
+#POSTGRES_DATAFEEDER_DB=georchestra
+
+### PostgreSQL - Data database
+# Database where imported/published datasets are written.
+# If any of these is left unset, it falls back to the matching
+# POSTGRES_DATAFEEDER_* value (see _set_data_db_defaults).
+
+# Host of the data database. Default: same as POSTGRES_DATAFEEDER_HOST
 POSTGRES_DATA_HOST=localhost
+
+# Port of the data database. Default: same as POSTGRES_DATAFEEDER_PORT
 POSTGRES_DATA_PORT=5433
+
+# User of the data database. Default: same as POSTGRES_DATAFEEDER_USER
 POSTGRES_DATA_USER=postgres
+
+# Password of the data database. Default: same as POSTGRES_DATAFEEDER_PASSWORD
 POSTGRES_DATA_PASSWORD=mypassword
+
+# Name of the data database. Default: same as POSTGRES_DATAFEEDER_DB
 POSTGRES_DATA_DB=postgres
-# In local dev the source DB reuses the same PostgreSQL instance as the data DB.
-# In production these point to a separate external source database.
+
+# Source databases for the "database import" type, as a JSON object mapping a
+# key to a SQLAlchemy/PostgreSQL URI. The key (e.g. SOURCE_DB_1) must match the
+# Airflow connection name in airflow/files/conn.json.
+# Default: {} (empty)
 SOURCE_DATABASES={"SOURCE_DB_1": "postgresql://postgres:mypassword@localhost:5433/postgres"}
-#TASK_EXECUTOR=CELERY
+
+# When true, final tables are written to a schema named after the org short
+# name instead of the default "data" schema.
+# Default: false
+#USE_ORG_SCHEMA=false
+
+### GeoServer
+
+# Internal URL of the GeoServer instance, MUST be through the gateway.
+# Default: http://localhost:8080/geoserver
+#GEOSERVER_INTERNAL_URL=http://localhost:8080/geoserver
+
+# GeoServer administrator user. Default: testadmin
+#GEOSERVER_USER=testadmin
+
+# GeoServer administrator password. Default: testadmin
+#GEOSERVER_PASSWORD=testadmin
+
+### GeoNetwork
+
+# Internal URL of the GeoNetwork instance, MUST be through the gateway.
+# Default: http://localhost:8080/geonetwork
+#GEONETWORK_INTERNAL_URL=http://localhost:8080/geonetwork
+
+# GeoNetwork administrator user. Default: testadmin
+#GEONETWORK_USERNAME=testadmin
+
+# GeoNetwork administrator password. Default: testadmin
+#GEONETWORK_PASSWORD=testadmin
+
+# XSRF token sent to GeoNetwork. Any UUID is accepted.
+# Default: c9f33266-e242-4198-a18c-b01290dce5f1
+#GEONETWORK_XSRF_TOKEN=c9f33266-e242-4198-a18c-b01290dce5f1
+
+# Strategy used to synchronize metadata privileges with GeoNetwork groups.
+# Allowed values: ORG, ROLE
+# Default: ORG
+#GN_SYNC_MODE=ORG
+
+# Default GeoNetwork group name used when publishing metadata.
+# Default: sample
+METADATA_DEFAULT_GROUP_NAME=PSC
+
+### Console
+
+# Internal URL of the geOrchestra console.
+# Default: http://localhost:8085/console
+#CONSOLE_INTERNAL_URL=http://localhost:8085/console
+
+### Authorization UI filters
+
+# Regex used to filter metadata groups shown in the authorization UI.
+# Default: (empty, no filtering)
+#METADATA_GROUPS_LABEL_FILTER_REGEX=
+
+# Regex used to filter data groups shown in the GeoServer authorization UI.
+# Default: (empty, no filtering)
+#DATA_GROUPS_LABEL_FILTER_REGEX=
+